initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    software-properties-common \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+COPY src/ ./src/
+
+RUN pip3 install -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

README.md

@@ -1,2 +1,19 @@
-# tasktrack
-Track tracker application written in python with ML functionalities
+---
+title: DocsQA
+emoji: 📚
+colorFrom: red
+colorTo: red
+sdk: docker
+app_port: 8501
+tags:
+- streamlit
+pinned: false
+short_description: Upload a document and ask questions based on its content
+---
+
+# Welcome to Streamlit!
+
+Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+
+If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
+forums](https://discuss.streamlit.io).

requirements.txt

@@ -0,0 +1,10 @@
+altair
+pandas
+streamlit
+fastapi
+uvicorn
+langchain
+transformers
+sentence-transformers
+faiss-cpu
+langchain-community

src/streamlit_app.py

@@ -0,0 +1,133 @@
+import streamlit as st
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from langchain_community.llms import HuggingFacePipeline
+from transformers import pipeline
+
+# # ----------------------
+# # Helper: Load and process uploaded file
+# # ----------------------
+# def read_uploaded_file(uploaded_file):
+#     text = uploaded_file.read().decode("utf-8")
+#     docs = text.split("\n")
+#     return docs
+
+# # ----------------------
+# # Load lightweight LLM
+# # ----------------------e
+# @st.cache_resource
+# def load_llm():
+#     pipe = pipeline("text-generation", model="google/flan-t5-small", max_new_tokens=256)
+#     return HuggingFacePipeline(pipeline=pipe)
+
+# # ----------------------
+# # Build retriever from uploaded content
+# # ----------------------
+# def build_retriever(docs):
+#     embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+#     db = FAISS.from_texts(docs, embeddings)
+#     return db.as_retriever()
+
+# # ----------------------
+# # Streamlit UI
+# # ----------------------
+
+# uploaded_file = st.file_uploader("Upload a `.txt` file with agricultural content", type=["txt"])
+# query = st.text_input("Ask a question based on your uploaded file:")
+
+# # Check if user uploaded a file
+# if uploaded_file:
+#     docs = read_uploaded_file(uploaded_file)
+#     retriever = build_retriever(docs)
+#     llm = load_llm()
+#     qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+
+#     if query:
+#         with st.spinner("Generating answer..."):
+#             result = qa_chain.run(query)
+#         st.success(result)
+# else:
+#     st.info("Please upload a `.txt` file to begin.")
+
+
+# ----------------------
+# Sample Text Content
+# ----------------------
+SAMPLE_TEXT = """Fertilizers help improve soil nutrients and crop yield.
+Irrigation methods vary depending on climate and crop type.
+Crop rotation can enhance soil health and reduce pests.
+Composting is an organic way to enrich the soil.
+Weed management is essential for higher productivity."""
+
+EXAMPLE_QUESTIONS = [
+    "What is this document about?"
+    "What is the role of fertilizers in agriculture?",
+    "Why is crop rotation important?",
+    "How does composting help farming?",
+]
+
+# ----------------------
+# Helper: Read uploaded file
+# ----------------------
+def read_uploaded_file(uploaded_file):
+    text = uploaded_file.read().decode("utf-8")
+    docs = text.split("\n")
+    return docs
+
+# ----------------------
+# Load lightweight LLM
+# ----------------------
+@st.cache_resource
+def load_llm():
+    pipe = pipeline("text-generation", model="google/flan-t5-small", max_new_tokens=256)
+    return HuggingFacePipeline(pipeline=pipe)
+
+# extract 
+
+# ----------------------
+# Build retriever from uploaded content
+# ----------------------
+def build_retriever(docs):
+    # if docs.type == pdf
+    # use langchain pymupdf to extract the text from the document
+
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = FAISS.from_texts(docs, embeddings)
+    return db.as_retriever()
+
+# ----------------------
+# Streamlit UI
+# ----------------------
+st.title("DocsQA: Upload & Ask")
+
+st.markdown("Upload a text file and ask questions about its contents.")
+
+# Add sample file download button
+st.download_button(
+    label="📄 Download Sample File",
+    data=SAMPLE_TEXT,
+    file_name="sample_agri.txt",
+    mime="text/plain"
+)
+
+# Show example questions
+with st.expander("💡 Try example questions"):
+    for q in EXAMPLE_QUESTIONS:
+        st.markdown(f"- {q}")
+
+uploaded_file = st.file_uploader("Upload your `.txt` file", type=["txt"])
+query = st.text_input("Ask a question:")
+
+if uploaded_file:
+    docs = read_uploaded_file(uploaded_file)
+    retriever = build_retriever(docs)
+    llm = load_llm()
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+
+    if query:
+        with st.spinner("Generating answer..."):
+            result = qa_chain.run(query)
+        st.success(result)
+else:
+    st.info("Please upload a `.txt` file or use the sample provided.")